Skip to main content
Glama
LawrenceCirillo

QuickBase MCP Server

quickbase_create_field

Add a new field to a QuickBase table, specifying the field type, label, and attributes such as required or unique, to enhance data organization and structure.

Instructions

Create a new field in a table

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
choicesNoChoices for choice fields
fieldTypeYesType of field
formulaNoFormula for formula fields
labelYesField label/name
lookupFieldIdNoField ID for lookup fields
lookupTableIdNoTable ID for lookup fields
requiredNoWhether field is required
tableIdYesTable ID to add field to
uniqueNoWhether field must be unique

Implementation Reference

  • Core handler function that executes the QuickBase API call to create a new field, handling field types, properties, choices, formulas, and lookups.
    async createField(tableId: string, field: QuickBaseField): Promise<number> {
      const fieldData: any = {
        tableId,
        label: field.label,
        fieldType: field.fieldType,
        required: field.required,
        unique: field.unique
      };
    
      // Add field-specific properties
      if (field.choices && ['text_choice', 'multiselect'].includes(field.fieldType)) {
        fieldData.properties = {
          choices: field.choices
        };
      }
    
      if (field.formula && field.fieldType === 'formula') {
        fieldData.formula = field.formula;
      }
    
      if (field.lookupReference && field.fieldType === 'lookup') {
        fieldData.properties = {
          lookupReference: field.lookupReference
        };
      }
    
      const response = await this.axios.post('/fields', fieldData);
      return response.data.id;
    }
  • Zod schema for validating input parameters to the quickbase_create_field tool.
    const CreateFieldSchema = z.object({
      tableId: z.string().describe('Table ID to add field to'),
      label: z.string().describe('Field label/name'),
      fieldType: z.enum([
        'text', 'text_choice', 'text_multiline', 'richtext', 'numeric', 
        'currency', 'percent', 'date', 'datetime', 'checkbox', 'email', 
        'phone', 'url', 'address', 'file', 'lookup', 'formula', 'reference'
      ]).describe('Type of field'),
      required: z.boolean().default(false).describe('Whether field is required'),
      unique: z.boolean().default(false).describe('Whether field must be unique'),
      choices: z.array(z.string()).optional().describe('Choices for choice fields'),
      formula: z.string().optional().describe('Formula for formula fields'),
      lookupTableId: z.string().optional().describe('Table ID for lookup fields'),
      lookupFieldId: z.number().optional().describe('Field ID for lookup fields')
    });
  • MCP tool registration including name, description, and input schema for listTools response.
    {
      name: 'quickbase_create_field',
      description: 'Create a new field in a table',
      inputSchema: {
        type: 'object',
        properties: {
          tableId: { type: 'string', description: 'Table ID to add field to' },
          label: { type: 'string', description: 'Field label/name' },
          fieldType: { 
            type: 'string',
            enum: ['text', 'text_choice', 'text_multiline', 'richtext', 'numeric', 'currency', 'percent', 'date', 'datetime', 'checkbox', 'email', 'phone', 'url', 'address', 'file', 'lookup', 'formula', 'reference'],
            description: 'Type of field'
          },
          required: { type: 'boolean', description: 'Whether field is required', default: false },
          unique: { type: 'boolean', description: 'Whether field must be unique', default: false },
          choices: { type: 'array', items: { type: 'string' }, description: 'Choices for choice fields' },
          formula: { type: 'string', description: 'Formula for formula fields' },
          lookupTableId: { type: 'string', description: 'Table ID for lookup fields' },
          lookupFieldId: { type: 'number', description: 'Field ID for lookup fields' }
        },
        required: ['tableId', 'label', 'fieldType']
      }
    },
  • MCP server dispatch handler for the tool call, parsing arguments and invoking the QuickBaseClient.createField method.
    case 'quickbase_create_field':
      if (!args || typeof args !== 'object') {
        throw new Error('Invalid arguments');
      }
      const fieldId = await this.qbClient.createField(args.tableId as string, {
        label: args.label as string,
        fieldType: args.fieldType as any,
        required: (args.required as boolean) || false,
        unique: (args.unique as boolean) || false,
        choices: args.choices as string[],
        formula: args.formula as string,
        lookupReference: args.lookupTableId ? {
          tableId: args.lookupTableId as string,
          fieldId: args.lookupFieldId as number
        } : undefined
      });
      return {
        content: [
          {
            type: 'text',
            text: `Field created with ID: ${fieldId}`,
          },
        ],
      };
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. While 'Create' implies a mutation operation, it doesn't specify whether this requires admin permissions, what happens on failure (e.g., duplicate labels), or if there are rate limits. For a tool that modifies database structure, this is a significant gap in safety and operational context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no wasted words. It's front-loaded with the core action and resource, making it easy to parse quickly. Every part of the sentence directly contributes to understanding the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of creating a database field (9 parameters, no output schema, and no annotations), the description is insufficient. It lacks details on behavioral traits (e.g., permissions, side effects), usage context relative to siblings, and expected outcomes. For a mutation tool with multiple parameters, this leaves too many gaps for reliable agent operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, meaning all parameters are documented in the input schema itself. The description adds no additional parameter information beyond the basic purpose, so it doesn't compensate for or enhance the schema. This meets the baseline score of 3 for high schema coverage without extra value from the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Create') and resource ('new field in a table'), making the purpose immediately understandable. However, it doesn't differentiate this tool from its sibling 'quickbase_create_lookup_field' or 'quickbase_create_advanced_relationship', which also create fields or field-like structures, leaving some ambiguity about when to choose this specific tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'quickbase_create_lookup_field' or 'quickbase_update_field'. It also doesn't mention prerequisites (e.g., needing table permissions) or typical use cases (e.g., adding custom fields to a table). This lack of context makes it harder for an agent to decide when this tool is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/LawrenceCirillo/QuickBase-MCP-Server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server